Agricultural data integration and analysis platform

Abstract

Provided herein are methods, systems, and media that implement machine learning algorithms to determine a cultivar regimen recommendation for a crop based on crop yield and cultivar condition data.

1 .- 29 . (canceled) 
     
     
         30 . A computer-implemented method of determining a cultivar regimen recommendation for a crop, the method comprising:
 a) receiving a plurality of current cultivar conditions from an internet of things sensor;   b) applying a first machine learning algorithm to at least a portion of the current cultivar conditions to determine the cultivar regimen recommendation;   c) receiving a verified crop yield after the cultivar regimen recommendation has been performed on the crop;   d) feeding back the verified crop yield to improve the first machine learning algorithm's calculation over time; and   e) transmitting the cultivar regimen recommendation.   
     
     
         31 . The method of  claim 30 , wherein the first machine learning algorithm is trained by:
 a) collecting from a database a plurality of historical growing conditions, wherein each historical growing condition comprises a historical cultivar condition and a historical cultivar regimen, and wherein the historical growing condition is associated with a historical crop yield;   b) creating a first training set comprising:
 i) a first plurality the collected historical growing conditions wherein each historical growing condition is associated with the historical crop yield; and 
 ii) a second plurality the collected historical growing conditions wherein each historical growing condition is disassociated from the historical crop yield; 
   c) training the first machine learning algorithm in a first stage using the first training set to determine a predicted crop yield;   d) creating a second training set for a second stage of training comprising the first training set and one or more of the second plurality of the collected historical growing conditions wherein a difference between the determined crop yield and the predicted crop yield is greater than a set amount; and   e) training the first machine learning algorithm in a second stage using the second training set.   
     
     
         32 . The method of  claim 30 , wherein the first machine learning algorithm is trained by:
 a) creating an initial cultivar model by assigning a probability weight to each of two or more predictor variables, the two or more predictor variable comprising:
 i) a historical cultivar condition; and 
 ii) a historical cultivar regimen; 
   b) using the initial cultivar model to determine a predicted historical crop yield;   c) receiving a historical crop yield; and   d) adjusting the probability weights based on the verified historical crop yield and the predicted historical crop yield.   
     
     
         33 . The method of  claim 30 , wherein the first machine learning algorithm comprises a neural network. 
     
     
         34 . The method of  claim 30 , further comprising:
 a) receiving a plurality of historical cultivar regimens, wherein each historical cultivar regimen comprises a plurality of historical regimen categories, wherein each historical regimen category comprises a plurality of cultivar instructions, and wherein each cultivar instruction is associated with a crop and a historical categorical crop yield;   b) applying a second machine learning algorithm to each cultivar instruction in one historical regimen category to determine an agricultural relationship between one or more of the cultivar instructions, the crop, and the associated historical categorical crop yield;   c) receiving a verified categorical crop yield after the cultivar instructions have been performed on the crop; and   d) appending the verified categorical crop yield to the historical categorical crop yield and appending the associated cultivar instructions to the historical regimen category to improve the second machine learning algorithm's calculation over time;   wherein the second machine learning algorithm determines the cultivar regimen recommendation based on the agricultural relationship.   
     
     
         35 . The method of  claim 34 , wherein the second machine learning algorithm comprises a neural network. 
     
     
         36 . The method of  claim 34 , wherein the second machine learning algorithm is trained by:
 a) creating an initial categorical model by assigning a probability weight to each of the plurality of cultivar instructions;   b) using the initial categorical model to determine a predicted categorical crop yield;   c) receiving a verified categorical crop yield; and   d) adjusting the probability weights based on the verified categorical crop yield and the predicted categorical crop yield.   
     
     
         37 . The method of  claim 30 , wherein the current cultivar condition, the historical cultivar condition, or both comprises a wind speed, a wind direction, a gust speed, a gust direction, a rainfall quantity, a soil moisture, a light measurement, a humidity, a crop dimension, a soil pH, a gamma-ray measurement, a picture, an audio track, a video, aerial imagery, satellite imagery, a chemical composition, an atmospheric pressure, an O 2  quantity, a N 2  quantity, a CO 2  quantity, a sporadic light measurement, a fruit growth measurement, a reflectance, an infrared measurement, a mid-infrared measurement, near-infrared measurement, a fruit density, a GPS position, a temperature, or any combination thereof. 
     
     
         38 . The method of  claim 30 , wherein the current cultivar condition is further received from a sensor, a weather information service, or both. 
     
     
         39 . The method of  claim 38 , wherein the sensor comprises at least one of a wind gauge, a rain gauge, a soil moisture gauge, a light gauge, a humidity gauge, a stem water potential dendrometer, a dendrometer, a GPS sensor, a pH meter, a gamma-ray sensor, a camera, a microphone, a video camera, a hyperspectral camera, an aerial camera, a satellite imaging device, a chemical sensor, an atmospheric pressure sensor, an O 2  sensor, a N 2  sensor, a CO 2  sensor, a sporadic light sensor, a fruit growth sensor, a reflectance sensor, an infrared sensor, an irrigation sensor, a mid-infrared sensor, near-infrared sensor, a fruit density sensor, or a thermometer. 
     
     
         40 . (canceled) 
     
     
         41 . The method of  claim 38 , wherein the sensor is coupled to the crop, a soil surrounding the crop, a remotely operated vehicle (ROV), an aerial drone, a balloon, or any combination thereof. 
     
     
         42 . The method of  claim 38 , further comprising displaying the cultivar condition on a dashboard. 
     
     
         43 . The method of  claim 42 , further comprising emitting an alarm if one or more of the plurality of current cultivar conditions is outside a predetermined range. 
     
     
         44 . The method of  claim 30 , wherein the current cultivar condition is received from a remote monitoring source. 
     
     
         45 . The method of  claim 44 , wherein the remote monitoring source is a weather monitoring source, and wherein the current cultivar condition is a temperature, a humidity, a wind speed, a wind direction, a rain quantity, a snow quantity, a hail quantity, or any combination thereof. 
     
     
         46 . The method of  claim 30 , wherein the current cultivar condition is received in real-time or near real-time. 
     
     
         47 . The method of  claim 30 , wherein the current cultivar condition is received periodically. 
     
     
         48 . The method of  claim 47 , wherein the period is at most about 1 minute, 5 minutes, 10 minutes, 15 minutes, 30 minutes, 1 hour, 2 hours, 6 hours, 12 hours, 1 day, 2 days, 3 days, or 1 week. 
     
     
         49 . The method of  claim 30 , wherein the current cultivar condition, the historical cultivar condition, or both comprises a condition of a single plant. 
     
     
         50 . The method of  claim 30 , wherein the current cultivar condition, the historical cultivar condition, or both comprises a condition of a single plant and a GPS location of the single plant. 
     
     
         51 . The method of  claim 50 , wherein the GPS location has a resolution of about 0.15 meters to about 5 meters. 
     
     
         52 . The method of  claim 30 , wherein the current cultivar condition, the historical cultivar condition, or both comprises a condition of a plurality of plants. 
     
     
         53 . The method of  claim 30 , wherein the current cultivar condition, the historical cultivar condition, or both comprises a condition of a field of plants. 
     
     
         54 . The method of  claim 30 , wherein the cultivar regimen recommendation, the historical cultivar regimen, or both comprises a fertilizer quantity adjustment, a fertilizer type adjustment, a pruning quantity adjustment, a pruning location adjustment, a pesticide quantity adjustment, a pesticide type adjustment, a planting date adjustment, a harvesting date adjustment, an irrigation quantity adjustment, an irrigation time of day adjustment, an irrigation schedule adjustment, a crop type adjustment, or any combination thereof. 
     
     
         55 . The method of  claim 30 , wherein the cultivar regimen recommendation comprises a reflection adjustment recommendation comprising a modification of a reflective property of a reflective surface configured to reflect light to a plant. 
     
     
         56 . The method of  claim 55 , wherein the reflective property comprises at least one of a light direction, a light wavelength range, a light intensity, or a light concentration. 
     
     
         57 . The method of  claim 55 , wherein the light comprises at least one of a modifiable light, sunlight, UV light, IR light, an electric light, or an LED light. 
     
     
         58 . The method of  claim 30 , wherein the cultivar regimen recommendation, the historical cultivar regimen, or both comprises an adjustment of the cultivar of a single plant. 
     
     
         59 . The method of  claim 30 , wherein the cultivar regimen recommendation, the historical cultivar regimen, or both comprises an adjustment of the cultivar of a plurality of plants. 
     
     
         60 . The method of  claim 30 , wherein the cultivar regimen recommendation, the historical cultivar regimen, or both comprises an adjustment of the cultivar of a field of plants. 
     
     
         61 . The method of  claim 30 , wherein the verified crop yield, the historical crop yield, or both comprises a crop yield quantity, a crop yield quality, or both. 
     
     
         62 . The method of  claim 61 , wherein the crop yield quality comprises a growth speed, a plant size, a leaf diameter, a plant height, a plant mass, a leaf color, a leaf shape, a plant stem water potential, a plant color, a plant shape, a plant condition, a fruit size, a fruit color, a fruit ripeness, a fruit acidity, a fruit antioxidant content, a fruit sugar content, a fruit density, a GPS position, a foliage density, a stem elongation rate, a reflectance spectra, a fruit density, a GPS position, an acid content, a dry matter content, a root growth rate, a root biomass, a root water content, a root depth, a root volume, a root size, a root density, a foliage reflectance spectra, a normalized difference vegetation index, an interior fruit temperature, an exterior fruit temperature, a red reflectance, an infrared reflectance, mid-infrared reflectance, a near-infrared reflectance, or any combination thereof. 
     
     
         63 . The method of  claim 61 , wherein the crop yield quality comprises a fruit yield. 
     
     
         64 . The method of  claim 30 , wherein transmitting the cultivar regimen recommendation comprises transmitting the cultivar regimen recommendation to a user via a graphical user interface (GUI). 
     
     
         65 . The method of  claim 30 , further comprising calculating an amount of CO 2  sequestration based on one or both of the verified crop yield and the plurality of cultivar conditions. 
     
     
         66 . The method of  claim 65 , further comprising providing the calculated amount of CO 2  sequestration to the first machine learning algorithm to adjust the cultivar regimen recommendation to optimize an amount of CO 2  sequestration. 
     
     
         67 . The method of  claim 65 , wherein the calculated amount of CO 2  is based on 1) cultivar conditions such as sensor data and/or 2) verified crop yield such as plant size, a leaf diameter, a plant height, a plant mass, a leaf shape, a plant shape, a plant condition, a fruit size, a fruit ripeness, a fruit density, a foliage density, a stem elongation rate, a reflectance spectra, a fruit density, a dry matter content, a root growth rate, a root biomass, a root water content, a root depth, a root volume, a root size, a root density, a foliage reflectance spectra, a normalized difference vegetation index, or a combination thereof. 
     
     
         68 . A computer-implemented system comprising: a digital processing device comprising: at least one processor, an operating system configured to perform executable instructions, a memory, and a computer program including instructions executable by the digital processing device to create an application to determine a cultivar regimen recommendation for a crop, the application configured to perform at least the following:
 a) receiving a plurality current cultivar conditions;   b) applying a first machine learning algorithm to at least a portion of the current cultivar conditions to determine the cultivar regimen recommendation;   c) receiving a verified crop yield after the cultivar regimen recommendation has been performed on the crop;   d) feeding back the verified crop yield to improve the first machine learning algorithm's calculation over time; and   e) transmitting the cultivar regimen recommendation.   
     
     
         69 .- 104 . (canceled) 
     
     
         105 . A non-transitory computer-readable storage media encoded with a computer program including instructions executable by a processor to create an application to determine a cultivar regimen recommendation for a crop, the application configured to perform at least the following:
 a) receiving a plurality current cultivar conditions;   b) applying a first machine learning algorithm to at least a portion of the current cultivar conditions to determine the cultivar regimen recommendation;   c) receiving a verified crop yield after the cultivar regimen recommendation has been performed on the crop;   d) feeding back the verified crop yield to improve the first machine learning algorithm's calculation over time; and   e) transmitting the cultivar regimen recommendation.   
     
     
         106 .- 142 . (canceled) 
     
     
         143 . A computer-implemented method of training a neural network for determining a cultivar regimen recommendation, the method comprising:
 a) collecting from a database a plurality of historical growing conditions, wherein each historical growing condition comprises a historical cultivar condition and a historical cultivar regimen, and wherein the historical growing condition is associated with a historical crop yield;   b) creating a first training set comprising:
 i) a first plurality the collected historical growing conditions wherein each historical growing condition is associated with the historical crop yield; and 
 ii) a second plurality the collected historical growing conditions wherein each historical growing condition is disassociated from the historical crop yield; 
   c) training the neural network in a first stage using the first training set to determine a predicted crop yield;   d) creating a second training set for a second stage of training comprising the first training set and one or more of the second plurality of the collected historical growing conditions wherein a difference between the determined crop yield and the predicted crop yield is greater than a set amount; and   e) training the neural network in a second stage using the second training set;
 wherein the cultivar regimen recommendation, the historical cultivar regimen, or both comprise a fertilizer quantity adjustment, a fertilizer type adjustment, a pruning quantity adjustment, a pruning location adjustment, a pesticide quantity adjustment, a pesticide type adjustment, a planting date adjustment, a harvesting date adjustment, an irrigation quantity adjustment, an irrigation time of day adjustment, an irrigation schedule adjustment, a crop type adjustment, or any combination thereof; and 
 wherein the historical growing condition comprises a wind speed, a wind direction, a gust speed, a gust direction, a rainfall quantity, a soil moisture, a light measurement, a humidity, a crop dimension, a soil pH, subsurface plant and/or tree root growth and propagation, above surface plant and/or tree growth and propagation (for e.g., plant stem, tree trunk), soil textural properties (e.g., lithology of soil), soil temperature, soil ion concentration, soil pore fluid composition, a gamma-ray measurement, a picture, an audio track, a video, aerial imagery, satellite imagery, a chemical composition, an atmospheric pressure, an O 2  quantity, a N 2  quantity, a CO 2  quantity, a sporadic light measurement, a fruit growth measurement, a reflectance, an infrared measurement, a mid-infrared measurement, near-infrared measurement, a fruit density, a GPS position, a temperature, or any combination thereof. 
   
     
     
         144 . A computer-implemented system comprising: a digital processing device comprising: at least one processor, an operating system configured to perform executable instructions, a memory, and a computer program including instructions executable by the digital processing device to create an application to train a neural network to determine a cultivar regimen recommendation, the application configured to perform at least the following:
 a) collecting from a database a plurality of historical growing conditions, wherein each historical growing condition comprises a historical cultivar condition and a historical cultivar regimen, and wherein the historical growing condition is associated with a historical crop yield;   b) creating a first training set comprising:
 i) a first plurality the collected historical growing conditions wherein each historical growing condition is associated with the historical crop yield; and 
 ii) a second plurality the collected historical growing conditions wherein each historical growing condition is disassociated from the historical crop yield; 
   c) training the neural network in a first stage using the first training set to determine a predicted crop yield;   d) creating a second training set for a second stage of training comprising the first training set and one or more of the second plurality of the collected historical growing conditions wherein a difference between the determined crop yield and the predicted crop yield is greater than a set amount; and   e) training the neural network in a second stage using the second training set;
 wherein the cultivar regimen recommendation, the historical cultivar regimen, or both comprise a fertilizer quantity adjustment, a fertilizer type adjustment, a pruning quantity adjustment, a pruning location adjustment, a pesticide quantity adjustment, a pesticide type adjustment, a planting date adjustment, a harvesting date adjustment, an irrigation quantity adjustment, an irrigation time of day adjustment, an irrigation schedule adjustment, a crop type adjustment, or any combination thereof; and 
 wherein the historical growing condition comprises a wind speed, a wind direction, a gust speed, a gust direction, a rainfall quantity, a soil moisture, a light measurement, a humidity, a crop dimension, a soil pH, subsurface plant and/or tree root growth and propagation, above surface plant and/or tree growth and propagation (for e.g., plant stem, tree trunk), soil textural properties (e.g., lithology of soil), soil temperature, soil ion concentration, soil pore fluid composition, a gamma-ray measurement, a picture, an audio track, a video, aerial imagery, satellite imagery, a chemical composition, an atmospheric pressure, an O 2  quantity, a N 2  quantity, a CO 2  quantity, a sporadic light measurement, a fruit growth measurement, a reflectance, an infrared measurement, a mid-infrared measurement, near-infrared measurement, a fruit density, a GPS position, a temperature, or any combination thereof. 
   
     
     
         145 . A non-transitory computer-readable storage media encoded with a computer program including instructions executable by a processor to create an application to train a neural network to determine a cultivar regimen recommendation, the application configured to perform at least the following:
 a) collecting from a database a plurality of historical growing conditions, wherein each historical growing condition comprises a historical cultivar condition and a historical cultivar regimen, and wherein the historical growing condition is associated with a historical crop yield;   b) creating a first training set comprising:
 i) a first plurality the collected historical growing conditions wherein each historical growing condition is associated with the historical crop yield; and 
 ii) a second plurality the collected historical growing conditions wherein each historical growing condition is disassociated from the historical crop yield; 
   c) training the neural network in a first stage using the first training set to determine a predicted crop yield;   d) creating a second training set for a second stage of training comprising the first training set and one or more of the second plurality of the collected historical growing conditions wherein a difference between the determined crop yield and the predicted crop yield is greater than a set amount; and   e) training the neural network in a second stage using the second training set;
 wherein the cultivar regimen recommendation, the historical cultivar regimen, or both comprise a fertilizer quantity adjustment, a fertilizer type adjustment, a pruning quantity adjustment, a pruning location adjustment, a pesticide quantity adjustment, a pesticide type adjustment, a planting date adjustment, a harvesting date adjustment, an irrigation quantity adjustment, an irrigation time of day adjustment, an irrigation schedule adjustment, a crop type adjustment, or any combination thereof; and 
 wherein the historical growing condition comprises a wind speed, a wind direction, a gust speed, a gust direction, a rainfall quantity, a soil moisture, a light measurement, a humidity, a crop dimension, a soil pH, subsurface plant and/or tree root growth and propagation, above surface plant and/or tree growth and propagation (for e.g., plant stem, tree trunk), soil textural properties (e.g., lithology of soil), soil temperature, soil ion concentration, soil pore fluid composition, a gamma-ray measurement, a picture, an audio track, a video, aerial imagery, satellite imagery, a chemical composition, an atmospheric pressure, an O 2  quantity, a N 2  quantity, a CO 2  quantity, a sporadic light measurement, a fruit growth measurement, a reflectance, an infrared measurement, a mid-infrared measurement, near-infrared measurement, a fruit density, a GPS position, a temperature, or any combination thereof. 
   
     
     
         146 . A computer-implemented system comprising: a digital processing device comprising: at least one processor, an operating system configured to perform executable instructions, a memory, and a computer program including instructions executable by the digital processing device to create an application for cultivating a crop, the application configured to perform at least the following:
 a) deploying a plurality of sensors to measure a current cultivar condition of the crop;   b) receiving a historical cultivar regimen associated with a historical crop yield;   c) applying an algorithm to determine a cultivar regimen recommendation based on the current cultivar condition, the current cultivar regimen, and the historical cultivar regimen; and   d) altering a cultivar condition of the crop by performing the cultivar regimen recommendation.   
     
     
         147 .- 175 . (canceled)